Argumentative Text Generation in Economic Domain

TL;DR

This paper presents a method for argument text generation in the economic domain using fine-tuned Russian language models, achieving over 20% improvement in accuracy compared to baseline models.

Contribution

It introduces a novel approach of annotating economic news with argumentation using translated corpora and fine-tuning language models for improved argument generation in Russian.

Findings

Argument generation accuracy improved by 20 percentage points

Fine-tuning on annotated economic news enhances argument quality

Method demonstrates effective adaptation of language models to domain-specific argumentation

Abstract

The development of large and super-large language models, such as GPT-3, T5, Switch Transformer, ERNIE, etc., has significantly improved the performance of text generation. One of the important research directions in this area is the generation of texts with arguments. The solution of this problem can be used in business meetings, political debates, dialogue systems, for preparation of student essays. One of the main domains for these applications is the economic sphere. The key problem of the argument text generation for the Russian language is the lack of annotated argumentation corpora. In this paper, we use translated versions of the Argumentative Microtext, Persuasive Essays and UKP Sentential corpora to fine-tune RuBERT model. Further, this model is used to annotate the corpus of economic news by argumentation. Then the annotated corpus is employed to fine-tune the ruGPT-3 model, which generates argument texts. The results show that this approach improves the accuracy of the argument generation by more than 20 percentage points (63.2\% vs. 42.5\%) compared to the original ruGPT-3 model.